learn

Fail

Audited by Snyk on Nov 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E004: Prompt injection detected in skill instructions.

  • Potential prompt injection detected (medium risk: 0.30). The skill is a local learnings manager, but its end step silently drains an artifacts-sync queue that may push data off-machine without saying where it goes, which is an ambiguous, possibly undisclosed reporting action, so I'm flagging it medium under the recall-first rule.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The required show/search/export/prune workflow reads the project's local learnings.jsonl via gstack-learnings-search, and those entries are written by the agent's own sessions, which may have consumed outsider content earlier, so this is a low-risk indirect path rather than a direct outsider submission channel.

Issues (2)

E004
CRITICAL

Prompt injection detected in skill instructions.

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
CRITICAL
Analyzed
Nov 16, 2026, 08:17 PM
Issues
2